linux_dsm_epyc7002/fs
Nick Piggin 3e880fb5e4 fs: use fast counters for vfs caches
percpu_counter library generates quite nasty code, so unless you need
to dynamically allocate counters or take fast approximate value, a
simple per cpu set of counters is much better.

The percpu_counter can never be made to work as well, because it has an
indirection from pointer to percpu memory, and it can't use direct
this_cpu_inc interfaces because it doesn't use static PER_CPU data, so
code will always be worse.

In the fastpath, it is the difference between this:

        incl %gs:nr_dentry      # nr_dentry

and this:

        movl    percpu_counter_batch(%rip), %edx        # percpu_counter_batch,
        movl    $1, %esi        #,
        movq    $nr_dentry, %rdi        #,
        call    __percpu_counter_add    # (plus I clobber registers)

__percpu_counter_add:
        pushq   %rbp    #
        movq    %rsp, %rbp      #,
        subq    $32, %rsp       #,
        movq    %rbx, -24(%rbp) #,
        movq    %r12, -16(%rbp) #,
        movq    %r13, -8(%rbp)  #,
        movq    %rdi, %rbx      # fbc, fbc
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
        movq %gs:kernel_stack,%rax      #, pfo_ret__
# 0 "" 2
#NO_APP
        incl    -8124(%rax)     # <variable>.preempt_count
        movq    32(%rdi), %r12  # <variable>.counters, tcp_ptr__
#APP
# 78 "lib/percpu_counter.c" 1
        add %gs:this_cpu_off, %r12      # this_cpu_off, tcp_ptr__
# 0 "" 2
#NO_APP
        movslq  (%r12),%r13     #* tcp_ptr__, tmp73
        movslq  %edx,%rax       # batch, batch
        addq    %rsi, %r13      # amount, count
        cmpq    %rax, %r13      # batch, count
        jge     .L27    #,
        negl    %edx    # tmp76
        movslq  %edx,%rdx       # tmp76, tmp77
        cmpq    %rdx, %r13      # tmp77, count
        jg      .L28    #,
.L27:
        movq    %rbx, %rdi      # fbc,
        call    _raw_spin_lock  #
        addq    %r13, 8(%rbx)   # count, <variable>.count
        movq    %rbx, %rdi      # fbc,
        movl    $0, (%r12)      #,* tcp_ptr__
        call    _raw_spin_unlock        #
.L29:
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
        movq %gs:kernel_stack,%rax      #, pfo_ret__
# 0 "" 2
#NO_APP
        decl    -8124(%rax)     # <variable>.preempt_count
        movq    -8136(%rax), %rax       #, D.14625
        testb   $8, %al #, D.14625
        jne     .L32    #,
.L31:
        movq    -24(%rbp), %rbx #,
        movq    -16(%rbp), %r12 #,
        movq    -8(%rbp), %r13  #,
        leave
        ret
        .p2align 4,,10
        .p2align 3
.L28:
        movl    %r13d, (%r12)   # count,*
        jmp     .L29    #
.L32:
        call    preempt_schedule        #
        .p2align 4,,6
        jmp     .L31    #
        .size   __percpu_counter_add, .-__percpu_counter_add
        .p2align 4,,15

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:17 +11:00
..
9p convert v9fs 2010-10-29 04:16:38 -04:00
adfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
affs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
afs convert afs 2010-10-29 04:17:13 -04:00
autofs4 autofs4 - remove ioctl mutex (bz23142) 2010-12-07 07:45:44 -08:00
befs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
bfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
btrfs Fix btrfs b0rkage 2010-12-20 09:09:57 -08:00
cachefiles llseek: automatically add .llseek fop 2010-10-15 15:53:27 +02:00
ceph ceph: mark user pages dirty on direct-io reads 2010-12-17 09:54:40 -08:00
cifs cifs: remove bogus remapping of error in cifs_filldir() 2010-12-08 18:47:54 +00:00
coda convert get_sb_nodev() users 2010-10-29 04:16:31 -04:00
configfs convert get_sb_single() users 2010-10-29 04:16:28 -04:00
cramfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
debugfs convert get_sb_single() users 2010-10-29 04:16:28 -04:00
devpts convert get_sb_single() users 2010-10-29 04:16:28 -04:00
dlm Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/dlm 2010-10-22 17:33:16 -07:00
ecryptfs BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
efs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
exofs convert get_sb_nodev() users 2010-10-29 04:16:31 -04:00
exportfs exportfs: use dget_parent 2010-10-25 21:26:13 -04:00
ext2 new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
ext3 BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
ext4 ext4: fix on-line resizing regression 2010-12-23 15:00:54 -05:00
fat new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
freevxfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
fscache Add a dummy printk function for the maintenance of unused printks 2010-08-12 09:51:35 -07:00
fuse fuse: verify ioctl retries 2010-11-30 16:39:27 +01:00
gfs2 GFS2: Userland expects quota limit/warn/usage in 512b blocks 2010-11-19 11:20:29 +00:00
hfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
hfsplus new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
hostfs convert get_sb_nodev() users 2010-10-29 04:16:31 -04:00
hpfs Merge branches 'irq-core-for-linus' and 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2010-10-31 20:40:24 -04:00
hppfs convert get_sb_nodev() users 2010-10-29 04:16:31 -04:00
hugetlbfs hugetlbfs: lessen the impact of a deprecation warning 2010-11-12 07:55:32 -08:00
isofs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
jbd Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6 2010-10-27 20:13:18 -07:00
jbd2 jbd2: fix /proc/fs/jbd2/<dev> when using an external journal 2010-11-17 21:46:26 -05:00
jffs2 Merge git://git.infradead.org/mtd-2.6 2010-10-30 08:31:35 -07:00
jfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
lockd BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
logfs logfs: fix "Kernel BUG at readwrite.c:1193" 2010-12-22 19:43:33 -08:00
minix new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
ncpfs BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
nfs NFS: Fix panic after nfs_umount() 2010-12-10 13:01:50 -05:00
nfs_common
nfsd nfsd: Fix possible BUG_ON firing in set_change_info 2010-12-08 11:44:04 -05:00
nilfs2 nilfs2: fix regression of garbage collection ioctl 2010-12-16 14:35:18 +09:00
nls
notify fanotify: fill in the metadata_len field on struct fanotify_event_metadata 2010-12-15 13:58:18 -05:00
ntfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
ocfs2 Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2 2010-12-23 16:36:48 -08:00
omfs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
openpromfs sparc: fix openpromfs compile 2010-11-08 14:29:39 -08:00
partitions Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block 2010-10-25 07:45:10 -07:00
proc Revert "vfs: show unreachable paths in getcwd and proc" 2010-12-05 16:39:45 -08:00
qnx4 new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
quota quota: Fix possible oops in __dquot_initialize() 2010-10-28 01:30:06 +02:00
ramfs convert get_sb_nodev() users 2010-10-29 04:16:31 -04:00
reiserfs reiserfs: don't acquire lock recursively in reiserfs_acl_chmod 2010-12-02 14:51:15 -08:00
romfs convert get_sb_mtd() users to ->mount() 2010-10-29 04:16:26 -04:00
squashfs Merge git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-linus 2010-10-29 08:48:58 -07:00
sysfs convert sysfs 2010-10-29 04:17:08 -04:00
sysv new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
ubifs convert ubifs 2010-10-29 04:16:36 -04:00
udf new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
ufs new helper: mount_bdev() 2010-10-29 04:16:13 -04:00
xfs xfs: log timestamp changes to the source inode in rename 2010-12-09 17:07:02 -06:00
aio.c new helper: ihold() 2010-10-25 21:26:11 -04:00
anon_inodes.c convert get_sb_pseudo() users 2010-10-29 04:16:33 -04:00
attr.c check ATTR_SIZE contraints in inode_change_ok 2010-08-09 16:47:39 -04:00
bad_inode.c bkl: Remove locked .ioctl file operation 2010-08-14 00:24:24 +02:00
binfmt_aout.c Don't dump task struct in a.out core-dumps 2010-10-14 10:57:40 -07:00
binfmt_elf_fdpic.c
binfmt_elf.c ARM: 6342/1: fix ASLR of PIE executables 2010-10-08 10:02:53 +01:00
binfmt_em86.c
binfmt_flat.c
binfmt_misc.c convert get_sb_single() users 2010-10-29 04:16:28 -04:00
binfmt_script.c Make do_execve() take a const filename pointer 2010-08-17 18:07:43 -07:00
binfmt_som.c
bio-integrity.c fs/bio-integrity.c: return -ENOMEM on kmalloc failure 2010-08-23 13:36:59 +02:00
bio.c bio: take care not overflow page count when mapping/copying user data 2010-11-10 14:40:43 +01:00
block_dev.c BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
buffer.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6 2010-10-26 17:58:44 -07:00
char_dev.c Merge branch 'llseek' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/bkl 2010-10-22 10:52:56 -07:00
compat_binfmt_elf.c
compat_ioctl.c BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
compat.c exec: copy-and-paste the fixes into compat_do_execve() paths 2010-11-30 17:56:38 -08:00
dcache.c fs: use fast counters for vfs caches 2011-01-07 17:50:17 +11:00
dcookies.c
direct-io.c fs/direct-io.c: fix truncation error in dio_complete() return 2010-10-26 16:52:13 -07:00
drop_caches.c simplify checks for I_CLEAR/I_FREEING 2010-08-09 16:47:44 -04:00
eventfd.c llseek: automatically add .llseek fop 2010-10-15 15:53:27 +02:00
eventpoll.c epoll: make epoll_wait() use the hrtimer range feature 2010-10-27 18:03:18 -07:00
exec.c install_special_mapping skips security_file_mmap check. 2010-12-15 12:30:36 -08:00
fcntl.c fasync: Fix placement of FASYNC flag comment 2010-10-27 18:17:02 -07:00
fifo.c llseek: automatically add .llseek fop 2010-10-15 15:53:27 +02:00
file_table.c fs: allow for more than 2^31 files 2010-10-26 16:52:15 -07:00
file.c vfs: use kmalloc() to allocate fdmem if possible 2010-08-11 08:59:02 -07:00
filesystems.c
fs_struct.c fs: fs_struct rwlock to spinlock 2010-08-18 08:35:46 -04:00
fs-writeback.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable 2010-10-30 09:05:48 -07:00
generic_acl.c vfs: update ctime when changing the file's permission by setfacl 2010-08-18 01:04:22 -04:00
inode.c fs: use fast counters for vfs caches 2011-01-07 17:50:17 +11:00
internal.h braino in internal.h 2010-10-29 05:49:13 -04:00
ioctl.c Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 2010-11-19 19:46:45 -08:00
ioprio.c ioprio: grab rcu_read_lock in sys_ioprio_{set,get}() 2010-11-15 10:23:31 +01:00
Kconfig Merge 'staging-next' to Linus's tree 2010-10-28 09:44:56 -07:00
Kconfig.binfmt coredump: default CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y 2010-10-27 18:03:12 -07:00
libfs.c convert get_sb_pseudo() users 2010-10-29 04:16:33 -04:00
locks.c BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
Makefile Merge 'staging-next' to Linus's tree 2010-10-28 09:44:56 -07:00
mbcache.c mbcache: Limit the maximum number of cache entries 2010-08-18 06:24:41 -04:00
mpage.c
namei.c fanotify: if set by user unset FMODE_NONOTIFY before fsnotify_perm() is called 2010-12-07 16:14:21 -05:00
namespace.c BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
nfsctl.c
no-block.c llseek: automatically add .llseek fop 2010-10-15 15:53:27 +02:00
open.c fix open/umount race 2010-10-29 04:14:56 -04:00
pipe.c Un-inline get_pipe_info() helper function 2010-11-28 16:27:19 -08:00
pnode.c fs: brlock vfsmount_lock 2010-08-18 08:35:48 -04:00
pnode.h
posix_acl.c
read_write.c BKL: remove extraneous #include <smp_lock.h> 2010-11-17 08:59:32 -08:00
read_write.h
readdir.c vfs: fix warning: 'dirent' is used uninitialized in this function 2010-08-09 20:45:05 -07:00
select.c epoll: make epoll_wait() use the hrtimer range feature 2010-10-27 18:03:18 -07:00
seq_file.c fs: take dcache_lock inside __d_path 2010-10-25 21:26:12 -04:00
signalfd.c Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6 2010-10-26 10:13:10 -07:00
splice.c Export 'get_pipe_info()' to other users 2010-11-28 14:09:57 -08:00
stack.c
stat.c Mark arguments to certain syscalls as being const 2010-08-13 16:53:13 -07:00
statfs.c add f_flags to struct statfs(64) 2010-08-09 16:48:44 -04:00
super.c switch get_sb_ns() users 2010-10-29 04:17:03 -04:00
sync.c get rid of file_fsync() 2010-08-09 16:47:43 -04:00
timerfd.c llseek: automatically add .llseek fop 2010-10-15 15:53:27 +02:00
utimes.c Mark arguments to certain syscalls as being const 2010-08-13 16:53:13 -07:00
xattr_acl.c
xattr.c